--- JSON-XS/XS.pm 2007/05/09 16:10:37 1.33 +++ JSON-XS/XS.pm 2007/12/19 11:42:52 1.79 @@ -2,6 +2,9 @@ JSON::XS - JSON serialising/deserialising, done correctly and fast +JSON::XS - 正しくて高速な JSON シリアライザ/デシリアライザ + (http://fleur.hio.jp/perldoc/mix/lib/JSON/XS.html) + =head1 SYNOPSIS use JSON::XS; @@ -9,12 +12,8 @@ # exported functions, they croak on error # and expect/generate UTF-8 - $utf8_encoded_json_text = to_json $perl_hash_or_arrayref; - $perl_hash_or_arrayref = from_json $utf8_encoded_json_text; - - # objToJson and jsonToObj aliases to to_json and from_json - # are exported for compatibility to the JSON module, - # but should not be used in new code. + $utf8_encoded_json_text = encode_json $perl_hash_or_arrayref; + $perl_hash_or_arrayref = decode_json $utf8_encoded_json_text; # OO-interface @@ -22,12 +21,28 @@ $pretty_printed_unencoded = $coder->encode ($perl_scalar); $perl_scalar = $coder->decode ($unicode_json_text); + # Note that JSON version 2.0 and above will automatically use JSON::XS + # if available, at virtually no speed overhead either, so you should + # be able to just: + + use JSON; + + # and do the same things, except that you have a pure-perl fallback now. + =head1 DESCRIPTION This module converts Perl data structures to JSON and vice versa. Its primary goal is to be I and its secondary goal is to be I. To reach the latter goal it was written in C. +Beginning with version 2.0 of the JSON module, when both JSON and +JSON::XS are installed, then JSON will fall back on JSON::XS (this can be +overriden) with no overhead due to emulation (by inheritign constructor +and methods). If JSON::XS is not available, it will fall back to the +compatible JSON::PP module as backend, so using JSON instead of JSON::XS +gives you a portable JSON API that can be fast when you need and doesn't +require a C compiler when that is a problem. + As this is the n-th-something JSON module on CPAN, what was the reason to write yet another JSON module? While it seems there are many JSON modules, none of them correctly handle all corner cases, and in most cases @@ -43,7 +58,7 @@ =over 4 -=item * correct unicode handling +=item * correct Unicode handling This module knows how to handle Unicode, and even documents how and when it does so. @@ -73,10 +88,10 @@ =item * reasonably versatile output formats -You can choose between the most compact guarenteed single-line format +You can choose between the most compact guaranteed single-line format possible (nice for simple line-based protocols), a pure-ascii format (for when your transport is not 8-bit clean, still supports the whole -unicode range), or a pretty-printed format (for when you want to read that +Unicode range), or a pretty-printed format (for when you want to read that stuff). Or you can combine those features in whatever way you like. =back @@ -87,29 +102,35 @@ use strict; -BEGIN { - our $VERSION = '1.12'; - our @ISA = qw(Exporter); +our $VERSION = '2.01'; +our @ISA = qw(Exporter); + +our @EXPORT = qw(encode_json decode_json to_json from_json); - our @EXPORT = qw(to_json from_json objToJson jsonToObj); - require Exporter; +sub to_json($) { + require Carp; + Carp::croak ("JSON::XS::to_json has been renamed to encode_json, either downgrade to pre-2.0 versions of JSON::XS or rename the call"); +} - require XSLoader; - XSLoader::load JSON::XS::, $VERSION; +sub from_json($) { + require Carp; + Carp::croak ("JSON::XS::from_json has been renamed to decode_json, either downgrade to pre-2.0 versions of JSON::XS or rename the call"); } +use Exporter; +use XSLoader; + =head1 FUNCTIONAL INTERFACE -The following convinience methods are provided by this module. They are +The following convenience methods are provided by this module. They are exported by default: =over 4 -=item $json_text = to_json $perl_scalar +=item $json_text = encode_json $perl_scalar -Converts the given Perl data structure (a simple scalar or a reference to -a hash or array) to a UTF-8 encoded, binary string (that is, the string contains -octets only). Croaks on error. +Converts the given Perl data structure to a UTF-8 encoded, binary string +(that is, the string contains octets only). Croaks on error. This function call is functionally identical to: @@ -117,11 +138,11 @@ except being faster. -=item $perl_scalar = from_json $json_text +=item $perl_scalar = decode_json $json_text -The opposite of C: expects an UTF-8 (binary) string and tries to -parse that as an UTF-8 encoded JSON text, returning the resulting simple -scalar or reference. Croaks on error. +The opposite of C: expects an UTF-8 (binary) string and tries +to parse that as an UTF-8 encoded JSON text, returning the resulting +reference. Croaks on error. This function call is functionally identical to: @@ -129,9 +150,66 @@ except being faster. +=item $is_boolean = JSON::XS::is_bool $scalar + +Returns true if the passed scalar represents either JSON::XS::true or +JSON::XS::false, two constants that act like C<1> and C<0>, respectively +and are used to represent JSON C and C values in Perl. + +See MAPPING, below, for more information on how JSON values are mapped to +Perl. + =back +=head1 A FEW NOTES ON UNICODE AND PERL + +Since this often leads to confusion, here are a few very clear words on +how Unicode works in Perl, modulo bugs. + +=over 4 + +=item 1. Perl strings can store characters with ordinal values > 255. + +This enables you to store Unicode characters as single characters in a +Perl string - very natural. + +=item 2. Perl does I associate an encoding with your strings. + +Unless you force it to, e.g. when matching it against a regex, or printing +the scalar to a file, in which case Perl either interprets your string as +locale-encoded text, octets/binary, or as Unicode, depending on various +settings. In no case is an encoding stored together with your data, it is +I that decides encoding, not any magical metadata. + +=item 3. The internal utf-8 flag has no meaning with regards to the +encoding of your string. + +Just ignore that flag unless you debug a Perl bug, a module written in +XS or want to dive into the internals of perl. Otherwise it will only +confuse you, as, despite the name, it says nothing about how your string +is encoded. You can have Unicode strings with that flag set, with that +flag clear, and you can have binary data with that flag set and that flag +clear. Other possibilities exist, too. + +If you didn't know about that flag, just the better, pretend it doesn't +exist. + +=item 4. A "Unicode String" is simply a string where each character can be +validly interpreted as a Unicode codepoint. + +If you have UTF-8 encoded data, it is no longer a Unicode string, but a +Unicode string encoded in UTF-8, giving you a binary string. + +=item 5. A string containing "high" (> 255) character values is I a UTF-8 string. + +It's a fact. Learn to live with it. + +=back + +I hope this helps :) + + =head1 OBJECT-ORIENTED INTERFACE The object oriented interface lets you configure your own encoding or @@ -152,12 +230,14 @@ =item $json = $json->ascii ([$enable]) +=item $enabled = $json->get_ascii + If C<$enable> is true (or missing), then the C method will not generate characters outside the code range C<0..127> (which is ASCII). Any -unicode characters outside that range will be escaped using either a +Unicode characters outside that range will be escaped using either a single \uXXXX (BMP characters) or a double \uHHHH\uLLLLL escape sequence, as per RFC4627. The resulting encoded JSON text can be treated as a native -unicode string, an ascii-encoded, latin1-encoded or UTF-8 encoded string, +Unicode string, an ascii-encoded, latin1-encoded or UTF-8 encoded string, or any other superset of ASCII. If C<$enable> is false, then the C method will not escape Unicode @@ -173,12 +253,14 @@ =item $json = $json->latin1 ([$enable]) +=item $enabled = $json->get_latin1 + If C<$enable> is true (or missing), then the C method will encode the resulting JSON text as latin1 (or iso-8859-1), escaping any characters outside the code range C<0..255>. The resulting string can be treated as a -latin1-encoded JSON text or a native unicode string. The C method +latin1-encoded JSON text or a native Unicode string. The C method will not be affected in any way by this flag, as C by default -expects unicode, which is a strict superset of latin1. +expects Unicode, which is a strict superset of latin1. If C<$enable> is false, then the C method will not escape Unicode characters unless required by the JSON syntax or other flags. @@ -187,7 +269,7 @@ text, as most octets will not be escaped, resulting in a smaller encoded size. The disadvantage is that the resulting JSON text is encoded in latin1 (and must correctly be treated as such when storing and -transfering), a rare encoding for JSON. It is therefore most useful when +transferring), a rare encoding for JSON. It is therefore most useful when you want to store data structures known to contain binary data efficiently in files or databases, not when talking to other JSON encoders/decoders. @@ -196,6 +278,8 @@ =item $json = $json->utf8 ([$enable]) +=item $enabled = $json->get_utf8 + If C<$enable> is true (or missing), then the C method will encode the JSON result into UTF-8, as required by many protocols, while the C method expects to be handled an UTF-8-encoded string. Please @@ -205,8 +289,8 @@ and UTF-32 encoding families, as described in RFC4627. If C<$enable> is false, then the C method will return the JSON -string as a (non-encoded) unicode string, while C expects thus a -unicode string. Any decoding or encoding (e.g. to UTF-8 or UTF-16) needs +string as a (non-encoded) Unicode string, while C expects thus a +Unicode string. Any decoding or encoding (e.g. to UTF-8 or UTF-16) needs to be done yourself, e.g. using the Encode module. Example, output UTF-16BE-encoded JSON: @@ -238,17 +322,21 @@ =item $json = $json->indent ([$enable]) +=item $enabled = $json->get_indent + If C<$enable> is true (or missing), then the C method will use a multiline format as output, putting every array member or object/hash key-value pair -into its own line, identing them properly. +into its own line, indenting them properly. If C<$enable> is false, no newlines or indenting will be produced, and the -resulting JSON text is guarenteed not to contain any C. +resulting JSON text is guaranteed not to contain any C. This setting has no effect when decoding JSON texts. =item $json = $json->space_before ([$enable]) +=item $enabled = $json->get_space_before + If C<$enable> is true (or missing), then the C method will add an extra optional space before the C<:> separating keys from values in JSON objects. @@ -264,6 +352,8 @@ =item $json = $json->space_after ([$enable]) +=item $enabled = $json->get_space_after + If C<$enable> is true (or missing), then the C method will add an extra optional space after the C<:> separating keys from values in JSON objects and extra whitespace after the C<,> separating key-value pairs and array @@ -278,8 +368,57 @@ {"key": "value"} +=item $json = $json->relaxed ([$enable]) + +=item $enabled = $json->get_relaxed + +If C<$enable> is true (or missing), then C will accept some +extensions to normal JSON syntax (see below). C will not be +affected in anyway. I. I suggest only to use this option to +parse application-specific files written by humans (configuration files, +resource files etc.) + +If C<$enable> is false (the default), then C will only accept +valid JSON texts. + +Currently accepted extensions are: + +=over 4 + +=item * list items can have an end-comma + +JSON I array elements and key-value pairs with commas. This +can be annoying if you write JSON texts manually and want to be able to +quickly append elements, so this extension accepts comma at the end of +such items not just between them: + + [ + 1, + 2, <- this comma not normally allowed + ] + { + "k1": "v1", + "k2": "v2", <- this comma not normally allowed + } + +=item * shell-style '#'-comments + +Whenever JSON allows whitespace, shell-style comments are additionally +allowed. They are terminated by the first carriage-return or line-feed +character, after which more white-space and comments are allowed. + + [ + 1, # this comment not allowed in JSON + # neither this one... + ] + +=back + =item $json = $json->canonical ([$enable]) +=item $enabled = $json->get_canonical + If C<$enable> is true (or missing), then the C method will output JSON objects by sorting their keys. This is adding a comparatively high overhead. @@ -289,13 +428,15 @@ This option is useful if you want the same data structure to be encoded as the same JSON text (given the same overall settings). If it is disabled, -the same hash migh be encoded differently even if contains the same data, +the same hash might be encoded differently even if contains the same data, as key-value pairs have no inherent ordering in Perl. This setting has no effect when decoding JSON texts. =item $json = $json->allow_nonref ([$enable]) +=item $enabled = $json->get_allow_nonref + If C<$enable> is true (or missing), then the C method can convert a non-reference into its corresponding string, number or null JSON value, which is an extension to RFC4627. Likewise, C will accept those JSON @@ -312,8 +453,126 @@ JSON::XS->new->allow_nonref->encode ("Hello, World!") => "Hello, World!" +=item $json = $json->allow_blessed ([$enable]) + +=item $enabled = $json->get_allow_blessed + +If C<$enable> is true (or missing), then the C method will not +barf when it encounters a blessed reference. Instead, the value of the +B option will decide whether C (C +disabled or no C method found) or a representation of the +object (C enabled and C method found) is being +encoded. Has no effect on C. + +If C<$enable> is false (the default), then C will throw an +exception when it encounters a blessed object. + +=item $json = $json->convert_blessed ([$enable]) + +=item $enabled = $json->get_convert_blessed + +If C<$enable> is true (or missing), then C, upon encountering a +blessed object, will check for the availability of the C method +on the object's class. If found, it will be called in scalar context +and the resulting scalar will be encoded instead of the object. If no +C method is found, the value of C will decide what +to do. + +The C method may safely call die if it wants. If C +returns other blessed objects, those will be handled in the same +way. C must take care of not causing an endless recursion cycle +(== crash) in this case. The name of C was chosen because other +methods called by the Perl core (== not by the user of the object) are +usually in upper case letters and to avoid collisions with any C +function or method. + +This setting does not yet influence C in any way, but in the +future, global hooks might get installed that influence C and are +enabled by this setting. + +If C<$enable> is false, then the C setting will decide what +to do when a blessed object is found. + +=item $json = $json->filter_json_object ([$coderef->($hashref)]) + +When C<$coderef> is specified, it will be called from C each +time it decodes a JSON object. The only argument is a reference to the +newly-created hash. If the code references returns a single scalar (which +need not be a reference), this value (i.e. a copy of that scalar to avoid +aliasing) is inserted into the deserialised data structure. If it returns +an empty list (NOTE: I C, which is a valid scalar), the +original deserialised hash will be inserted. This setting can slow down +decoding considerably. + +When C<$coderef> is omitted or undefined, any existing callback will +be removed and C will not change the deserialised hash in any +way. + +Example, convert all JSON objects into the integer 5: + + my $js = JSON::XS->new->filter_json_object (sub { 5 }); + # returns [5] + $js->decode ('[{}]') + # throw an exception because allow_nonref is not enabled + # so a lone 5 is not allowed. + $js->decode ('{"a":1, "b":2}'); + +=item $json = $json->filter_json_single_key_object ($key [=> $coderef->($value)]) + +Works remotely similar to C, but is only called for +JSON objects having a single key named C<$key>. + +This C<$coderef> is called before the one specified via +C, if any. It gets passed the single value in the JSON +object. If it returns a single value, it will be inserted into the data +structure. If it returns nothing (not even C but the empty list), +the callback from C will be called next, as if no +single-key callback were specified. + +If C<$coderef> is omitted or undefined, the corresponding callback will be +disabled. There can only ever be one callback for a given key. + +As this callback gets called less often then the C +one, decoding speed will not usually suffer as much. Therefore, single-key +objects make excellent targets to serialise Perl objects into, especially +as single-key JSON objects are as close to the type-tagged value concept +as JSON gets (it's basically an ID/VALUE tuple). Of course, JSON does not +support this in any way, so you need to make sure your data never looks +like a serialised Perl hash. + +Typical names for the single object key are C<__class_whatever__>, or +C<$__dollars_are_rarely_used__$> or C<}ugly_brace_placement>, or even +things like C<__class_md5sum(classname)__>, to reduce the risk of clashing +with real hashes. + +Example, decode JSON objects of the form C<< { "__widget__" => } >> +into the corresponding C<< $WIDGET{} >> object: + + # return whatever is in $WIDGET{5}: + JSON::XS + ->new + ->filter_json_single_key_object (__widget__ => sub { + $WIDGET{ $_[0] } + }) + ->decode ('{"__widget__": 5') + + # this can be used with a TO_JSON method in some "widget" class + # for serialisation to json: + sub WidgetBase::TO_JSON { + my ($self) = @_; + + unless ($self->{id}) { + $self->{id} = ..get..some..id..; + $WIDGET{$self->{id}} = $self; + } + + { __widget__ => $self->{id} } + } + =item $json = $json->shrink ([$enable]) +=item $enabled = $json->get_shrink + Perl usually over-allocates memory a bit when allocating space for strings. This flag optionally resizes strings generated by either C or C to their minimum size possible. This can save @@ -340,6 +599,8 @@ =item $json = $json->max_depth ([$maximum_nesting_depth]) +=item $max_depth = $json->get_max_depth + Sets the maximum nesting level (default C<512>) accepted while encoding or decoding. If the JSON text or Perl data structure has an equal or higher nesting level then this limit, then the encoder and decoder will @@ -353,8 +614,25 @@ Setting the maximum depth to one disallows any nesting, so that ensures that the object is only a single hash/object or array. -The argument to C will be rounded up to the next nearest power -of two. +The argument to C will be rounded up to the next highest power +of two. If no argument is given, the highest possible setting will be +used, which is rarely useful. + +See SECURITY CONSIDERATIONS, below, for more info on why this is useful. + +=item $json = $json->max_size ([$maximum_string_size]) + +=item $max_size = $json->get_max_size + +Set the maximum length a JSON text may have (in bytes) where decoding is +being attempted. The default is C<0>, meaning no limit. When C +is called on a string longer then this number of characters it will not +attempt to decode the string but throw an exception. This setting has no +effect on C (yet). + +The argument to C will be rounded up to the next B +power of two (so may be more than requested). If no argument is given, the +limit check will be deactivated (same as when C<0> is specified). See SECURITY CONSIDERATIONS, below, for more info on why this is useful. @@ -376,6 +654,20 @@ Perl arrayrefs and JSON objects become Perl hashrefs. C becomes C<1>, C becomes C<0> and C becomes C. +=item ($perl_scalar, $characters) = $json->decode_prefix ($json_text) + +This works like the C method, but instead of raising an exception +when there is trailing garbage after the first JSON object, it will +silently stop parsing there and return the number of characters consumed +so far. + +This is useful if your JSON texts are not delimited by an outer protocol +(which is not the brightest thing to do in the first place) and you need +to know where the JSON text ends. + + JSON::XS->new->decode_prefix ("[1] the tail") + => ([], 3) + =back @@ -387,9 +679,10 @@ (what you put in comes out as something equivalent). For the more enlightened: note that in the following descriptions, -lowercase I refers to the Perl interpreter, while uppcercase I +lowercase I refers to the Perl interpreter, while uppercase I refers to the abstract Perl language itself. + =head2 JSON -> PERL =over 4 @@ -397,7 +690,7 @@ =item object A JSON object becomes a reference to a hash in Perl. No ordering of object -keys is preserved (JSON does not preserver object key ordering itself). +keys is preserved (JSON does not preserve object key ordering itself). =item array @@ -411,18 +704,30 @@ =item number -A JSON number becomes either an integer or numeric (floating point) -scalar in perl, depending on its range and any fractional parts. On the -Perl level, there is no difference between those as Perl handles all the -conversion details, but an integer may take slightly less memory and might -represent more values exactly than (floating point) numbers. +A JSON number becomes either an integer, numeric (floating point) or +string scalar in perl, depending on its range and any fractional parts. On +the Perl level, there is no difference between those as Perl handles all +the conversion details, but an integer may take slightly less memory and +might represent more values exactly than (floating point) numbers. + +If the number consists of digits only, JSON::XS will try to represent +it as an integer value. If that fails, it will try to represent it as +a numeric (floating point) value if that is possible without loss of +precision. Otherwise it will preserve the number as a string value. + +Numbers containing a fractional or exponential part will always be +represented as numeric (floating point) values, possibly at a loss of +precision. + +This might create round-tripping problems as numbers might become strings, +but as Perl is typeless there is no other way to do it. =item true, false -These JSON atoms become C<0>, C<1>, respectively. Information is lost in -this process. Future versions might represent those values differently, -but they will be guarenteed to act like these integers would normally in -Perl. +These JSON atoms become C and C, +respectively. They are overloaded to act almost exactly like the numbers +C<1> and C<0>. You can check whether a scalar is a JSON boolean by using +the C function. =item null @@ -430,6 +735,7 @@ =back + =head2 PERL -> JSON The mapping from Perl to JSON is slightly more difficult, as Perl is a @@ -461,7 +767,12 @@ C<1>, which get turned into C and C atoms in JSON. You can also use C and C to improve readability. - to_json [\0,JSON::XS::true] # yields [false,true] + encode_json [\0,JSON::XS::true] # yields [false,true] + +=item JSON::XS::true, JSON::XS::false + +These special values become JSON true and JSON false values, +respectively. You can also use C<\1> and C<\0> directly if you want. =item blessed objects @@ -477,32 +788,32 @@ before encoding as JSON strings and anything else as number value: # dump as number - to_json [2] # yields [2] - to_json [-3.0e17] # yields [-3e+17] - my $value = 5; to_json [$value] # yields [5] + encode_json [2] # yields [2] + encode_json [-3.0e17] # yields [-3e+17] + my $value = 5; encode_json [$value] # yields [5] # used as string, so dump as string print $value; - to_json [$value] # yields ["5"] + encode_json [$value] # yields ["5"] # undef becomes null - to_json [undef] # yields [null] + encode_json [undef] # yields [null] -You can force the type to be a string by stringifying it: +You can force the type to be a JSON string by stringifying it: my $x = 3.1; # some variable containing a number "$x"; # stringified $x .= ""; # another, more awkward way to stringify print $x; # perl does it for you, too, quite often -You can force the type to be a number by numifying it: +You can force the type to be a JSON number by numifying it: my $x = "3"; # some variable containing a string $x += 0; # numify it, ensuring it will be dumped as a number - $x *= 1; # same thing, the choise is yours. + $x *= 1; # same thing, the choice is yours. -You can not currently output JSON booleans or force the type in other, -less obscure, ways. Tell me if you need this capability. +You can not currently force the type in other, less obscure, ways. Tell me +if you need this capability. =back @@ -521,11 +832,11 @@ Slow (but very portable, as it is written in pure Perl). -Undocumented/buggy Unicode handling (how JSON handles unicode values is -undocumented. One can get far by feeding it unicode strings and doing -en-/decoding oneself, but unicode escapes are not working properly). +Undocumented/buggy Unicode handling (how JSON handles Unicode values is +undocumented. One can get far by feeding it Unicode strings and doing +en-/decoding oneself, but Unicode escapes are not working properly). -No roundtripping (strings get clobbered if they look like numbers, e.g. +No round-tripping (strings get clobbered if they look like numbers, e.g. the string C<2.0> will encode to C<2.0> instead of C<"2.0">, and that will decode into the number 2. @@ -535,7 +846,7 @@ Undocumented/buggy Unicode handling. -No roundtripping. +No round-tripping. Has problems handling many Perl values (e.g. regex results and other magic values will make it croak). @@ -555,11 +866,11 @@ single-line compact format for use in a protocol, and preferably a way to generate ASCII-only JSON texts). -Completely broken (and confusingly documented) Unicode handling (unicode +Completely broken (and confusingly documented) Unicode handling (Unicode escapes are not working properly, you need to set ImplicitUnicode to I values on en- and decoding to get symmetric behaviour). -No roundtripping (simple cases work, but this depends on wether the scalar +No round-tripping (simple cases work, but this depends on whether the scalar value was used in a numeric context or not). Dumping hashes may skip hash values depending on iterator state. @@ -569,7 +880,7 @@ Does not check input for validity (i.e. will accept non-JSON input and return "something" instead of raising an exception. This is a security -issue: imagine two banks transfering money between each other using +issue: imagine two banks transferring money between each other using JSON. One bank might parse a given non-JSON request and deduct money, while the other might reject the transaction with a syntax error. While a good protocol will at least recover, that is extra unnecessary work and @@ -579,12 +890,12 @@ Very fast. Very natural. Very nice. -Undocumented unicode handling (but the best of the pack. Unicode escapes +Undocumented Unicode handling (but the best of the pack. Unicode escapes still don't get parsed properly). Very inflexible. -No roundtripping. +No round-tripping. Does not generate valid JSON texts (key strings are often unquoted, empty keys result in nothing being output) @@ -593,6 +904,30 @@ =back + +=head2 JSON and YAML + +You often hear that JSON is a subset (or a close subset) of YAML. This is, +however, a mass hysteria and very far from the truth. In general, there is +no way to configure JSON::XS to output a data structure as valid YAML. + +If you really must use JSON::XS to generate YAML, you should use this +algorithm (subject to change in future versions): + + my $to_yaml = JSON::XS->new->utf8->space_after (1); + my $yaml = $to_yaml->encode ($ref) . "\n"; + +This will usually generate JSON texts that also parse as valid +YAML. Please note that YAML has hardcoded limits on (simple) object key +lengths that JSON doesn't have, so you should make sure that your hash +keys are noticeably shorter than the 1024 characters YAML allows. + +There might be other incompatibilities that I am not aware of. In general +you should not try to generate YAML with a JSON generator or vice versa, +or try to parse JSON with a YAML parser or vice versa: chances are high +that you will run into severe interoperability problems. + + =head2 SPEED It seems that JSON::XS is surprisingly fast, as shown in the following @@ -600,47 +935,57 @@ in the JSON::XS distribution, to make it easy to compare on your own system. -First comes a comparison between various modules using a very short JSON -string: +First comes a comparison between various modules using a very short +single-line JSON string: - {"method": "handleMessage", "params": ["user1", "we were just talking"], "id": null} + {"method": "handleMessage", "params": ["user1", "we were just talking"], \ + "id": null, "array":[1,11,234,-5,1e5,1e7, true, false]} -It shows the number of encodes/decodes per second (JSON::XS uses the -functional interface, while JSON::XS/2 uses the OO interface with -pretty-printing and hashkey sorting enabled). Higher is better: +It shows the number of encodes/decodes per second (JSON::XS uses +the functional interface, while JSON::XS/2 uses the OO interface +with pretty-printing and hashkey sorting enabled, JSON::XS/3 enables +shrink). Higher is better: module | encode | decode | -----------|------------|------------| - JSON | 11488.516 | 7823.035 | - JSON::DWIW | 94708.054 | 129094.260 | - JSON::PC | 63884.157 | 128528.212 | - JSON::Syck | 34898.677 | 42096.911 | - JSON::XS | 654027.064 | 396423.669 | - JSON::XS/2 | 371564.190 | 371725.613 | + JSON 1.x | 4990.842 | 4088.813 | + JSON::DWIW | 51653.990 | 71575.154 | + JSON::PC | 65948.176 | 74631.744 | + JSON::PP | 8931.652 | 3817.168 | + JSON::Syck | 24877.248 | 27776.848 | + JSON::XS | 388361.481 | 227951.304 | + JSON::XS/2 | 227951.304 | 218453.333 | + JSON::XS/3 | 338250.323 | 218453.333 | + Storable | 16500.016 | 135300.129 | -----------+------------+------------+ -That is, JSON::XS is more than six times faster than JSON::DWIW on -encoding, more than three times faster on decoding, and about thirty times -faster than JSON, even with pretty-printing and key sorting. +That is, JSON::XS is about five times faster than JSON::DWIW on encoding, +about three times faster on decoding, and over forty times faster +than JSON, even with pretty-printing and key sorting. It also compares +favourably to Storable for small amounts of data. Using a longer test string (roughly 18KB, generated from Yahoo! Locals search API (http://nanoref.com/yahooapis/mgPdGg): module | encode | decode | -----------|------------|------------| - JSON | 273.023 | 44.674 | - JSON::DWIW | 1089.383 | 1145.704 | - JSON::PC | 3097.419 | 2393.921 | - JSON::Syck | 514.060 | 843.053 | - JSON::XS | 6479.668 | 3636.364 | - JSON::XS/2 | 3774.221 | 3599.124 | + JSON 1.x | 55.260 | 34.971 | + JSON::DWIW | 825.228 | 1082.513 | + JSON::PC | 3571.444 | 2394.829 | + JSON::PP | 210.987 | 32.574 | + JSON::Syck | 552.551 | 787.544 | + JSON::XS | 5780.463 | 4854.519 | + JSON::XS/2 | 3869.998 | 4798.975 | + JSON::XS/3 | 5862.880 | 4798.975 | + Storable | 4445.002 | 5235.027 | -----------+------------+------------+ -Again, JSON::XS leads by far. +Again, JSON::XS leads by far (except for Storable which non-surprisingly +decodes faster). -On large strings containing lots of high unicode characters, some modules +On large strings containing lots of high Unicode characters, some modules (such as JSON::PC) seem to decode faster than JSON::XS, but the result -will be broken due to missing (or wrong) unicode handling. Others refuse +will be broken due to missing (or wrong) Unicode handling. Others refuse to decode or encode properly, so it was impossible to prepare a fair comparison table for that case. @@ -656,16 +1001,18 @@ Second, you need to avoid resource-starving attacks. That means you should limit the size of JSON texts you accept, or make sure then when your -resources run out, thats just fine (e.g. by using a separate process that +resources run out, that's just fine (e.g. by using a separate process that can crash safely). The size of a JSON text in octets or characters is usually a good indication of the size of the resources required to decode -it into a Perl structure. +it into a Perl structure. While JSON::XS can check the size of the JSON +text, it might be too late when you already have it in memory, so you +might want to check the size before you accept the string. Third, JSON::XS recurses using the C stack when decoding objects and arrays. The C stack is a limited resource: for instance, on my amd64 machine with 8MB of stack size I can decode around 180k nested arrays but only 14k nested JSON objects (due to perl itself recursing deeply on croak -to free the temporary). If that is exceeded, the program crashes. to be +to free the temporary). If that is exceeded, the program crashes. To be conservative, the default nesting limit is set to 512. If your process has a smaller stack, you should adjust this setting accordingly with the C method. @@ -674,6 +1021,24 @@ of. In that case, you get to keep the pieces. I am always open for hints, though... +If you are using JSON::XS to return packets to consumption +by JavaScript scripts in a browser you should have a look at +L to see whether +you are vulnerable to some common attack vectors (which really are browser +design bugs, but it is still you who will have to deal with it, as major +browser developers care only for features, not about getting security +right). + + +=head1 THREADS + +This module is I guaranteed to be thread safe and there are no +plans to change this until Perl gets thread support (as opposed to the +horribly slow so-called "threads" which are simply slow and bloated +process simulations - use fork, its I faster, cheaper, better). + +(It might actually work, but you have been warned). + =head1 BUGS @@ -682,10 +1047,31 @@ still relatively early in its development. If you keep reporting bugs they will be fixed swiftly, though. +Please refrain from using rt.cpan.org or any other bug reporting +service. I put the contact address into my modules for a reason. + =cut -sub true() { \1 } -sub false() { \0 } +our $true = do { bless \(my $dummy = 1), "JSON::XS::Boolean" }; +our $false = do { bless \(my $dummy = 0), "JSON::XS::Boolean" }; + +sub true() { $true } +sub false() { $false } + +sub is_bool($) { + UNIVERSAL::isa $_[0], "JSON::XS::Boolean" +# or UNIVERSAL::isa $_[0], "JSON::Literal" +} + +XSLoader::load "JSON::XS", $VERSION; + +package JSON::XS::Boolean; + +use overload + "0+" => sub { ${$_[0]} }, + "++" => sub { $_[0] = ${$_[0]} + 1 }, + "--" => sub { $_[0] = ${$_[0]} - 1 }, + fallback => 1; 1;